BOL: Related items

NVIDIA and Arc Institute Unveil Evo 2: A Breakthrough AI for DNA Design

BioStar — Fri, 21 Feb 2025 10:39:47 -0600

NVIDIA and the Arc Institute have introduced Evo 2, a groundbreaking AI model designed to understand, predict, and generate DNA sequences. This marks a major advancement in computational biology, offering scientists an unprecedented tool to decode the genetic blueprint of life and even design entirely new biological systems.

The Power of Evo 2: AI Meets DNA

Evo 2 is the largest AI model for biology ever created, trained on an astonishing 9.3 trillion DNA "letters" (nucleotides) carefully selected from genomes spanning the entire tree of life. This massive dataset ensures that Evo 2 can recognize patterns and relationships in genetic sequences at an unparalleled scale.

For the first time, scientists can design DNA with AI, moving beyond simple sequence analysis to active DNA generation. Evo 2 enables researchers to predict, modify, and even create entire genetic sequences, opening new possibilities in medicine, agriculture, and synthetic biology.

Decoding the Dark Genome

One of the biggest challenges in genetics is understanding the non-coding regions of DNA—vast stretches of the genome that do not code for proteins but play crucial roles in regulating gene expression. These regions control when and how genes are activated, influencing everything from development to disease.

Evo 2 is designed to decode these non-coding elements, helping researchers uncover their functions and use this knowledge to develop gene-based therapies, synthetic life forms, and precision agriculture solutions.

From Reading DNA to Writing It

To put Evo 2’s impact into perspective:

Previous AI models could "read" DNA like a book, analyzing genetic sequences and identifying patterns.
Evo 2 can "write" entirely new DNA, designing functional genes, chromosomes, and even full genomes from scratch.

This means scientists can now engineer biological systems with AI, designing new proteins, metabolic pathways, and genetic circuits to address real-world challenges.

A Step Toward Generative Biology

The Arc Institute describes Evo 2 as a major step toward "generative biology"—a revolutionary approach where AI is used to create novel biological structures rather than just analyzing existing ones. This could lead to breakthroughs such as:

New medicines: AI-generated enzymes and proteins tailored for targeted therapies.
Disease-resistant crops: Genetically optimized plants for higher yield and climate resilience.
Synthetic organisms: Custom-designed microbes for bioremediation, biofuel production, and industrial applications.

An Open-Source Revolution

Unlike many proprietary AI models, Evo 2 is open source, making its capabilities accessible to researchers worldwide. This democratization of AI-driven biology means that scientists from different disciplines can collaborate, experiment, and innovate, accelerating discoveries in genetic engineering and synthetic biology.

With Evo 2, the boundaries of what’s possible in DNA design, genetic engineering, and biological innovation are being redrawn. The future of life sciences is no longer just about understanding life’s code—it’s about writing it.

Kubeflow: an open, community driven project to make it easy to deploy and manage an ML stack on Kubernetes

BioStar — Fri, 16 Nov 2018 15:05:14 -0600

The Kubeflow project is dedicated to making deployments of machine learning (ML) workflows on Kubernetes simple, portable and scalable. Our goal is not to recreate other services, but to provide a straightforward way to deploy best-of-breed open-source systems for ML to diverse infrastructures. Anywhere you are running Kubernetes, you should be able to run Kubeflow.

Address of the bookmark: https://www.kubeflow.org/

ChIPBase: open database for studying the transcription factor binding sites and motifs

Abhi — Wed, 29 Dec 2021 05:36:03 -0600

ChIPBase v2.0 is an open database for studying the transcription factor binding sites and motifs, and decoding the transcriptional regulatory networks of lncRNAs, miRNAs, other ncRNAs and protein-coding genes from ChIP-seq data. Our database currently contains ~10,200 curated peak datasets derived from ChIP-seq methods in 10 species.

Address of the bookmark: https://rna.sysu.edu.cn/chipbase/

NASA Open Science Data Repository

Abhi — Wed, 18 Dec 2024 11:54:47 -0600

The NASA Open Science Data Repository (OSDR) enables access to space-related data from experiments and missions that investigate biological and health responses of terrestrial life to spaceflight. The goal of OSDR is to enable multi-modal and multi-hierarchical fundamental space life science data be reused toward basic science, applied science, and operational outcomes for space exploration and knowledge discovery. These data include ‘omics, phenotypic, physiological, behavioral, hardware, environmental telemetry; raw, processed; tabular, text, code, bioimaging, and video.

https://www.nasa.gov/reference/osdr-data-processing/

Address of the bookmark: https://www.nasa.gov/osdr/

The anatomy of successful computational biology software

Jitendra Narayan — Thu, 10 Oct 2013 11:53:08 -0500

Creators of software widely used in computational biology discuss the factors that contributed to their success

Nature Biotechnology spoke with Altschul and several other originators of computational biology software programs widely used today (Table 1). The conversations explored what makes certain software tools successful, the unique challenges of developing them for biological research and how the field of computational biology, as a whole, can move research agendas forward. What follows is an edited compilation of interviews.

Detail @ http://www.nature.com/nbt/journal/v31/n10/full/nbt.2721.html

News Source @ Nature

Ten recommendations for creating usable bioinformatics command line software

RAJESH DETROJA — Sun, 08 Jun 2014 10:06:26 -0500

Bioinformatics software varies greatly in quality. In terms of usability, the command line interface is the first experience a user will have of a tool. Unfortunately, this is often also the last time a tool will be used. Here I present ten recommendations for command line software author’s tools to follow, which I believe would greatly improve the uptake and usability of their products, waste less user’s time, and improve the quality of scientific analyses.

Address of the bookmark: http://www.gigasciencejournal.com/content/2/1/15?utm_content=buffer25ee0&utm_medium=social&utm_source=twitter.com&utm_campaign=buffer

GKNO

Neel — Fri, 20 May 2016 18:56:37 -0500

gkno opens the world of complex bioinformatic analysis to people of all level of computational expertise. This site contains documentation, tutorials and information on all the tools that comprise gkno.

http://gkno.me/how-to/install.html

http://gkno.me/software.html

Address of the bookmark: http://gkno.me/

EasyBuild

Jit — Fri, 27 Jan 2017 16:00:43 -0600

EasyBuild is a software build and installation framework that allows you to manage (scientific) software on High Performance Computing (HPC) systems in an efficient way.
A full list of supported software packages is available here.

Address of the bookmark: https://hpcugent.github.io/easybuild/

simNGS and simLibrary – Software for Simulating Next-Gen Sequencing Data

Jit — Tue, 28 Nov 2017 06:49:11 -0600

simNGS is software for simulating observations from Illumina sequencing machines using the statistical models behind the AYB base-calling software. By default, observations only incorporate noise due to sequencing and do not incorporate effects from more esoteric sources of noise that may be present in real data ("dust", bubbles, merged clusters, sequence-heterogeneous clusters, etc). Many of these additional sources may optionally applied.

simNGS takes fasta format sequences and a file describing the covariance of noise between bases and cycles observed in an actual run of the machine, randomly generates noisy intensities representing the signals for the sequence at each cycle and calculates likelihoods for all possible base calls.

Address of the bookmark: https://www.ebi.ac.uk/goldman-srv/simNGS/

EvidentialGene: tr2aacds, mRNA Transcript Assembly Software

Rahul Nayak — Tue, 08 May 2018 04:39:39 -0500

EvidentialGene is a genome informatics project, "Evidence Directed Gene Construction for Eukaryotes", to construct high quality, accurate gene sets for animals and plants, developed by Don Gilbert at Indiana University, see
http://arthropods.eugenes.org/EvidentialGene/

Construction refers to the combination of classical gene prediction, and more recent gene assembly (de-novo and genome-assisted) methods. The basic Evigene methods involve using available best-of-breed gene prediction and assembly software, combining all evidence for genes, from expressed sequences, genome assembly sequences, related species protein sequences, and any other, to annotate and score gene constructions. Over-produced constructions are classified by gene evidence for best qualities per "locus", including genome-aligned and gene-transcript aligned (genome-free) locus identification. All software developed for EvidentialGene is publicly available. See project wiki/blog for notes.

Download

http://arthropods.eugenes.org/EvidentialGene/trassembly.html

https://sourceforge.net/p/evidentialgene/blog/

Address of the bookmark: http://arthropods.eugenes.org/EvidentialGene/trassembly.html